CN117690122A - Channel obstacle detection system for archive warehouse - Google Patents
Channel obstacle detection system for archive warehouse Download PDFInfo
- Publication number
- CN117690122A CN117690122A CN202410147112.3A CN202410147112A CN117690122A CN 117690122 A CN117690122 A CN 117690122A CN 202410147112 A CN202410147112 A CN 202410147112A CN 117690122 A CN117690122 A CN 117690122A
- Authority
- CN
- China
- Prior art keywords
- article
- obstacle
- unit
- configuration
- channel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 230000003068 static effect Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims description 45
- 238000004364 calculation method Methods 0.000 claims description 38
- 230000004888 barrier function Effects 0.000 claims description 14
- 238000000034 method Methods 0.000 claims description 13
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 6
- 230000006855 networking Effects 0.000 claims description 6
- 238000012797 qualification Methods 0.000 claims description 6
- 238000002372 labelling Methods 0.000 claims description 4
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 229920006395 saturated elastomer Polymers 0.000 description 2
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000037361 pathway Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/653—Three-dimensional objects by matching three-dimensional models, e.g. conformal mapping of Riemann surfaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/70—Labelling scene content, e.g. deriving syntactic or semantic representations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
Abstract
The invention discloses a channel obstacle detection system for a file warehouse, which particularly relates to the technical field of image recognition, wherein a configuration article information input module is arranged to call configuration article information in the file warehouse, full-network retrieval is carried out based on functions and names of configuration articles, the retrieved configuration article information is recorded, a configuration article standard three-dimensional model reconstruction module is arranged to reconstruct a retrieved configuration article standard three-dimensional model based on the recorded retrieved article information, and the configuration article standard three-dimensional model is marked by using the configuration article functions, names and models, so that the accuracy of article recognition in the file warehouse is improved, the possibility of erroneously clearing useful articles is avoided, the potential safety hazard is reduced to a certain extent, and a channel obstacle judgment standard setting module is used for setting static obstacle judgment standards and dynamic obstacle judgment standards, so that the accurate distinction and detection of channel obstacles are facilitated.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a channel obstacle detection system for an archive warehouse.
Background
The current archive storehouse is often in a large amount of archive stack improper circumstances, and this also has caused very big hindrance for the passageway circulation that archive storehouse set up, arranges the manual work to carry out the inspection at archive storehouse and can consume a large amount of manpower resources and the timeliness that the passageway obstacle detected can receive certain influence, how to realize the intelligent recognition of archive storehouse passageway obstacle has become the hotspot problem.
The existing automatic obstacle detection system for the archive warehouse is characterized in that a sensor is installed on a channel of the archive warehouse to collect the position and the size of an obstacle on the channel in real time, collected channel obstacle information is compared with a preset channel obstacle, an alarm is sent to remind a worker to clear the obstacle when the obstacle information meets an obstacle judgment standard, and objects are reserved when the obstacle information does not meet the obstacle judgment standard.
However, the above system still has some problems: the system only judges whether the obstacle needs to be cleared according to the position and the size of the obstacle, does not recognize the attribute information of the objects on the channel, possibly causes a certain potential safety hazard, can not be ensured in the accuracy of obstacle detection, and can simultaneously remove the useful objects.
Disclosure of Invention
In order to overcome the above-mentioned drawbacks of the prior art, an embodiment of the present invention provides a system for detecting a passage obstacle for a file repository, so as to solve the above-mentioned problems in the prior art.
In order to achieve the above purpose, the present invention provides the following technical solutions: a pathway obstacle detection system for an archive warehouse, comprising:
a configuration article information input module: retrieving configuration article information in the archive warehouse, performing full network retrieval based on the function and the name of the configuration article, and recording the retrieved configuration article information;
configuring a standard three-dimensional model reconstruction module of the article: reconstructing the retrieved configuration article standard three-dimensional model based on the recorded retrieved article information, and marking the configuration article standard three-dimensional model by using the configuration article function, name and model;
the channel obstacle judgment standard setting module: the method comprises the steps of setting channel obstacle judging standards, wherein the channel obstacle judging standards comprise static obstacle judging standards and dynamic obstacle judging standards;
an article online monitoring module is configured: monitoring article information in the archive warehouse in real time by using cameras, and sending image data recorded by different cameras to an article information configuration identification module;
a configuration article information identification module: after a series of processing is carried out on the received image data, whether the articles in the archive warehouse are configured articles or not is identified, the configured articles display the identified names and the types of the articles, and the non-configured articles display the articles as non-archive warehouse configured articles;
the channel obstacle detection module: detecting a channel obstacle based on the configuration article information identification result, and sending an alarm when the channel obstacle is judged to exist;
the channel obstacle processing module: processing all existing channel barriers after receiving the alarm, and automatically recording the alarm receiving time and the channel barrier cleaning completion time;
the channel obstacle processing efficiency calculation module: calculating a comprehensive channel obstacle coefficient by using the non-archive storehouse object configuration obstacle coefficient, the archive storehouse object configuration obstacle coefficient and the dynamic obstacle coefficient when an alarm is sent, and calculating channel obstacle processing efficiency based on the comprehensive channel obstacle coefficient and channel obstacle processing time;
database: for recording data of all modules in the system.
Preferably, the configuration article information input module comprises a configuration article information calling unit, a networking searching unit, a searching information recording unit and a data output unit, wherein the configuration article information calling unit calls the name, model and function of the configuration article in the archive warehouse after being authorized; the networking retrieval unit is communicated with the Internet and then inputs the function and the name of the configuration object of the file warehouse to retrieve the information of the configuration object respectively; the searching information recording unit is used for recording the searched name and model of the configuration article, the size data of the contained accessories, the connecting mode of the used accessories and the full-angle overall appearance picture; and the data output unit sends the recorded retrieval information to a configuration article standard three-dimensional model reconstruction module.
Preferably, the configuration article standard three-dimensional model reconstruction module comprises a data receiving unit, an accessory model construction unit, a configuration article three-dimensional model combination unit, a finished product model qualification identification unit, a model marking unit and an automatic backup unit, wherein the data receiving unit is used for receiving the recorded retrieved configuration article name, model, contained accessory size data, used accessory connection mode and full-angle overall appearance picture; the accessory model building unit builds an accessory model in modeling software based on the size information of accessories contained in the article; the three-dimensional model combination unit of the configuration article assembles the accessory model according to the retrieved accessory connection mode; the finished product model qualification identifying unit acquires full-angle overall appearance pictures of the configured article finished product model obtained after combination, compares the full-angle overall appearance pictures with the retrieved article entity full-angle overall appearance pictures one by one, judges that the finished product model is qualified when the contrast difference of the two pictures is lower than the preset contrast difference of the pictures, reserves and identifies the qualified finished product model and marks the qualified finished product model as a configured article standard three-dimensional model, otherwise judges that the finished product model is unqualified, and needs to be reconstructed for the unqualified finished product model until the unqualified finished product model is qualified; the model labeling unit labels the standard three-dimensional model of the configuration object by using the function, the name and the model of the configuration object; the automatic backup unit is used for automatically backing up the standard three-dimensional model of the configuration object.
Preferably, the configuration article information identification module comprises a real-time image data receiving unit, a time frame ordering unit, an image segmentation unit, a plane contour information extraction unit, an article three-dimensional contour combination unit, an article three-dimensional contour cleaning unit, a three-dimensional contour information matching unit, an information identification unit and an identification result output unit, wherein the real-time image data receiving unit receives image data recorded by different cameras in real time; the time frame ordering unit orders the received image data according to the time frames, and uses different camera image data of the same time frame as the same group of image data and marks the same group of image data by the time frames; the image segmentation unit segments the acquired picture information by using a complex scene image semantic segmentation algorithm of the improved PSPNet to obtain multi-angle images of different articles; the plane contour information extraction unit is used for extracting plane contour information of the article; the article three-dimensional contour combining unit is used for combining and reconstructing the obtained article plane contour information with different angles to obtain an article three-dimensional contour; the article three-dimensional contour cleaning unit filters and denoises the reconstructed article three-dimensional contour to remove redundant contour points; the three-dimensional contour information matching unit matches the three-dimensional contour of the cleaned article with the contour of the standard three-dimensional model of the configured article, and counts the contour volume V of the three-dimensional contour of the article which can be overlapped with the contour of the standard three-dimensional model of the configured article ch And a contour volume V which cannot be coincident bc And calculates the profile matching degree alpha lk The specific formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the The information identification unit compares the calculated maximum profile matching degree with a preset profile matching degree, wherein two articles which are larger than or equal to the preset profile matching degree and are matched are the same article, the two articles which are smaller than the preset profile matching degree and are matched are not the same article, the name and the model of the matched article are displayed when the matching is successful, and the article is displayed as a non-archive storehouse configuration article when the matching is failed; the identification result output unit is used for outputting identificationAnd as a result, to a channel obstruction detection module.
Preferably, the channel obstacle detection module comprises an identification result receiving unit, a non-archive storehouse configuration object obstacle detection unit, an archive storehouse configuration object obstacle detection unit, a dynamic obstacle detection unit and an alarm output unit, wherein the identification result receiving unit is used for receiving real-time identification results of objects in the archive storehouse; the non-archival repository configuration object obstacle detection unit is used for detecting the actual residence time of the non-archival repository configuration object, and judging that the non-archival repository configuration object obstacle exists when the actual residence time is greater than or equal to the preset time, and the non-archival repository object configuration obstacle coefficient X FP The calculation formula of (2) is as follows:,n cl configuring the quantity of the articles for non-archive storehouse, T cli Configuring the actual residence time of the item for the ith non-archive warehouse, T yl For a preset maximum permissible dwell time, V cli Configuring the contour volume of the item for the ith non-archive storehouse, V kf The volume of the built-in space of the archive storehouse is; the archive storehouse configuration article obstacle detection unit is used for detecting the relation between the width, length and height of the archive storehouse configuration article on the channel and the actual passing width, length and height of the channel and respective preset values thereof, judging that the archive storehouse configuration article obstacle exists when the maximum allowable width, length and height of the archive storehouse configuration article on the channel area are larger than or equal to the preset values, and judging that the archive storehouse configuration article obstacle exists when the actual passing width, length and height of the channel area are smaller than or equal to the preset values DP The calculation formula of (2) is as follows: />,n dp Configuring the quantity of articles for the archive warehouse, V dpi Configuring the volume of the object for the ith archive storehouse, V td The specific calculation formula for the space volume of the channel area is as follows: />,A td 、B td 、C td The width, length and height of the channel region respectively; the dynamic obstacle detection unit detects the number n of real-time dynamic obstacles in the archive warehouse da And remaining channel usable area A sy Calculating the real-time dynamic obstacle distribution density F D The specific formula is as follows:the calculation formula of the available area of the residual channel is as follows: />,A FP Configuring the area of the articles on the access area for non-archival storage, A DP Allocating the area of the articles on the channel area for the archive warehouse, and calculating the real-time dynamic barrier distribution density F D And saturation dynamic barrier distribution density F Y Comparing, and judging that dynamic obstacle exists when the calculated value is larger than or equal to the preset value, wherein the dynamic obstacle coefficient X at the moment DT The calculation formula of (2) is as follows: />The method comprises the steps of carrying out a first treatment on the surface of the The alarm output unit sends an alarm to the archive warehouse management center when any one of the detection units detects an obstacle.
Preferably, the channel obstacle processing efficiency calculation module comprises a data calling unit, a comprehensive channel obstacle coefficient calculation unit and a channel obstacle processing efficiency calculation unit, wherein the data calling unit is used for calling non-archive storehouse object configuration obstacle coefficients, dynamic obstacle coefficients, alarm receiving time during channel obstacle processing and channel obstacle clearing completion time when sending an alarm; the comprehensive channel obstacle coefficient calculation unit is based on a non-archive storehouse object configuration obstacle coefficient X when sending an alarm FP Obstacle coefficient X for file warehouse configuration article DP Coefficient of dynamic disorder X DT Calculating the comprehensive channel obstruction coefficient X ZZ The specific formula of (2) is:e is a natural constant; the channel obstacle processing efficiency calculation unit is based on the comprehensive channel obstacle coefficient X ZZ Alarm receiving time T during lane obstacle handling js Channel obstacle clearing completion time T qw Calculating channel obstruction processing efficiency beta zc The specific formula of (2) is:。
the invention has the technical effects and advantages that:
the invention sets the configuration article information input module to retrieve the configuration article information in the archive storehouse, carries out full network retrieval based on the function and the name of the configuration article, records the retrieved configuration article information, sets the configuration article standard three-dimensional model reconstruction module to reconstruct the retrieved configuration article standard three-dimensional model based on the recorded retrieved article information and marks the configuration article standard three-dimensional model by using the function, the name and the model of the configuration article, is beneficial to improving the accuracy of article identification in the archive storehouse, avoids the possibility of erroneously clearing useful articles, reduces the potential safety hazard to a certain extent, sets the channel obstacle judgment standard setting module to set the channel obstacle judgment standard, the channel obstacle judgment standard comprises a static obstacle judgment standard and a dynamic obstacle judgment standard, is beneficial to realizing the accurate distinguishing and detection of the channel obstacle, the method is favorable for keeping the smoothness of the channel, the channel obstacle detection module is arranged to detect the channel obstacle based on the identification result of the configuration object information, the alarm is sent when the channel obstacle is judged to exist, the channel obstacle processing module is arranged to process all the existing channel obstacles after the alarm is received, the alarm receiving time and the channel obstacle clearing completion time are automatically recorded, the channel obstacle processing efficiency calculation module is arranged to calculate the comprehensive channel obstacle coefficient by the non-archive storehouse object configuration obstacle coefficient, the archive storehouse object configuration object obstacle coefficient and the dynamic obstacle coefficient when the alarm is sent, the channel obstacle processing efficiency is calculated based on the comprehensive channel obstacle coefficient and the channel obstacle processing time length, the channel obstacle processing timeliness and the reliability can be intuitively displayed based on the calculation result, the channel obstacle processing timeliness can be timely optimized when the calculation result does not accord with the expected, the safety and the management efficiency of the archive storehouse are improved.
Drawings
Fig. 1 is a block diagram of a system architecture of the present invention.
FIG. 2 is a flow chart of the system operation of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment as shown in fig. 1 provides a channel obstacle detection system for an archive storehouse, which comprises a configured article information input module, a configured article standard three-dimensional model reconstruction module, a channel obstacle judgment standard setting module, a configured article online monitoring module, a configured article information identification module, a channel obstacle detection module, a channel obstacle processing efficiency calculation module and a database, wherein the article information input module, the configured article standard three-dimensional model reconstruction module, the configured article information identification module, the channel obstacle detection module, the channel obstacle processing module and the channel obstacle processing efficiency calculation module are sequentially connected, the channel obstacle judgment standard setting module is connected with the channel obstacle detection module, the configured article online monitoring module is connected with the configured article information identification module, and all modules in the system are connected with the database.
And the configuration article information input module is used for retrieving the configuration article information in the archive warehouse, carrying out full network retrieval based on the functions and names of the configuration articles, and recording the retrieved configuration article information.
The configuration article information input module comprises a configuration article information calling unit, a networking searching unit, a searching information recording unit and a data output unit, wherein the configuration article information calling unit calls the name, model and function of the configuration article in the archive warehouse after being authorized; the networking retrieval unit is communicated with the Internet and then inputs the function and the name of the configuration object of the file warehouse to retrieve the information of the configuration object respectively; the searching information recording unit is used for recording the searched name and model of the configuration article, the size data of the contained accessories, the connecting mode of the used accessories and the full-angle overall appearance picture; and the data output unit sends the recorded retrieval information to a configuration article standard three-dimensional model reconstruction module.
And the configuration article standard three-dimensional model reconstruction module reconstructs the retrieved configuration article standard three-dimensional model based on the recorded retrieved article information and marks the configuration article standard three-dimensional model by using the function, the name and the model of the configuration article.
Further, the configuration article standard three-dimensional model reconstruction module comprises a data receiving unit, an accessory model construction unit, a configuration article three-dimensional model combination unit, a finished product model qualification identification unit and a model labeling unit, the automatic backup unit is used for receiving the recorded retrieved name and model of the configuration article, the size data of the contained accessories, the connection mode of the used accessories and the full-angle overall appearance picture; the accessory model building unit builds an accessory model in modeling software based on the size information of accessories contained in the article; the three-dimensional model combination unit of the configuration article assembles the accessory model according to the retrieved accessory connection mode; the finished product model qualification identifying unit acquires full-angle overall appearance pictures of the configured article finished product model obtained after combination, compares the full-angle overall appearance pictures with the retrieved article entity full-angle overall appearance pictures one by one, judges that the finished product model is qualified when the contrast difference of the two pictures is lower than the preset contrast difference of the pictures, reserves and identifies the qualified finished product model and marks the qualified finished product model as a configured article standard three-dimensional model, otherwise judges that the finished product model is unqualified, and needs to be reconstructed for the unqualified finished product model until the unqualified finished product model is qualified; the model labeling unit labels the standard three-dimensional model of the configuration object by using the function, the name and the model of the configuration object; the automatic backup unit is used for automatically backing up the standard three-dimensional model of the configuration object.
The channel obstacle determination standard setting module is used for setting channel obstacle determination standards, wherein the channel obstacle determination standards comprise static obstacle determination standards and dynamic obstacle determination standards.
In this embodiment, it should be specifically noted that the channel obstacle determination criterion setting module includes a channel information retrieving unit, a static obstacle determination criterion setting unit, a dynamic obstacle determination criterion setting unit, and an automatic storage unit, where the channel information retrieving unit is configured to retrieve a width, a length, and a height of a channel area; the static obstacle judgment standard setting unit is provided with different obstacle judgment standards for non-archival storehouse configuration articles and archival storehouse configuration articles, wherein the maximum allowable stay time is set for the non-archival storehouse configuration articles, the non-archival storehouse configuration article obstacle is judged to exist when the actual stay time of the non-archival storehouse articles is larger than or equal to the maximum allowable stay time, the archival storehouse configuration articles are provided with two obstacle judgment standards, one is provided with the maximum allowable width, length and height of the archival storehouse configuration articles on a channel, the other is provided with the minimum allowable width, length and height of the archival storehouse configuration articles on the effective passage space of the channel, the archival storehouse configuration article obstacle is judged to exist when the maximum allowable width, length and height of the archival storehouse configuration articles on a channel area are larger than or equal to preset values, and the archival storehouse configuration article obstacle is judged to exist when the actual passage width, length and height of the channel area are smaller than or equal to preset values, and the archival storehouse article obstacle is judged not to exist when the two obstacle judgment standards are not met; the dynamic obstacle judgment standard setting unit calculates a traffic area based on the traffic width and the traffic length of the channel area, sets a saturated dynamic obstacle distribution density based on the traffic area, and judges that dynamic obstacle exists when the actual dynamic obstacle distribution density is greater than or equal to the saturated obstacle distribution density; the automatic storage unit is used for automatically storing the set archive storehouse static obstacle judgment standard and dynamic obstacle judgment standard and marking by using the latest updating time.
The on-line monitoring module for the configured articles monitors the article information in the archive warehouse in real time by using the cameras, and sends the image data recorded by the different cameras to the identification module for the configured article information.
And the configured article information identification module is used for identifying whether the articles in the archive warehouse are configured articles or not after a series of processing is carried out on the received image data, and displaying the identified article names and the identified model numbers by the configured articles, wherein the non-configured article displays the articles which are configured articles of the non-archive warehouse.
Further, the configuration article information identification module comprises a real-time image data receiving unit, a time frame ordering unit, an image segmentation unit, a plane contour information extraction unit, an article three-dimensional contour combination unit, an article three-dimensional contour cleaning unit, a three-dimensional contour information matching unit, an information identification unit and an identification result output unit, wherein the real-time image data receiving unit receives image data recorded by different cameras in real time; the time frame ordering unit orders the received image data according to the time frames, and uses different camera image data of the same time frame as the same group of image data and marks the same group of image data by the time frames; the image segmentation unit segments the acquired picture information by using a complex scene image semantic segmentation algorithm of the improved PSPNet to obtain multi-angle images of different articles; the plane contour information extraction unit is used for extracting plane contour information of the article; the article three-dimensional contour combining unit is used for combining and reconstructing the obtained article plane contour information with different angles to obtain an article three-dimensional contour; the article three-dimensional contour cleaning unit filters and denoises the reconstructed article three-dimensional contour to remove redundant contour points; the three-dimensional contour information matching unit matches the three-dimensional contour of the cleaned article with the contour of the standard three-dimensional model of the configured article, and counts the contour volume V of the three-dimensional contour of the article which can be overlapped with the contour of the standard three-dimensional model of the configured article ch And a contour volume V which cannot be coincident bc And calculates the profile matching degree alpha lk The specific formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the The information identifying unit calculatesComparing the maximum profile matching degree with a preset profile matching degree, judging that two articles matched with the maximum profile matching degree are identical articles more than or equal to the preset profile matching degree, judging that the two matched articles are not identical articles less than the preset profile matching degree, displaying the names and the models of the matched articles when the matching is successful, and displaying that the articles are non-archive warehouse configuration articles when the matching is failed; the identification result output unit is used for outputting the identification result to the channel obstacle detection module.
The channel obstacle detection module detects the channel obstacle based on the configuration article information identification result, and sends an alarm when the channel obstacle is judged to exist.
Further, the channel obstacle detection module comprises an identification result receiving unit, a non-archive warehouse configuration article obstacle detection unit, an archive warehouse configuration article obstacle detection unit, a dynamic obstacle detection unit and an alarm output unit, wherein the identification result receiving unit is used for receiving real-time identification results of articles in the archive warehouse; the non-archival repository configuration object obstacle detection unit is used for detecting the actual residence time of the non-archival repository configuration object, and judging that the non-archival repository configuration object obstacle exists when the actual residence time is greater than or equal to the preset time, and the non-archival repository object configuration obstacle coefficient X FP The calculation formula of (2) is as follows:,n cl configuring the quantity of the articles for non-archive storehouse, T cli Configuring the actual residence time of the item for the ith non-archive warehouse, T yl For a preset maximum permissible dwell time, V cli Configuring the contour volume of the item for the ith non-archive storehouse, V kf The volume of the built-in space of the archive storehouse is; the archive storehouse allocation article obstacle detection unit is used for detecting the relation between the width, length and height of archive storehouse allocation articles on the channel and the actual passing width, length and height of the channel and the respective preset values, judging that the archive storehouse allocation articles are obstacle when the maximum allowable width, length and height of archive storehouse allocation articles on the channel area are larger than or equal to the preset values, and judging that the archive storehouse allocation articles are obstacle when the channel is in the process ofJudging that the file warehouse is provided with article barriers when the actual passing width, length and height of the area are smaller than or equal to preset values, wherein the file warehouse is provided with article barrier coefficients X DP The calculation formula of (2) is as follows: />,n dp Configuring the quantity of articles for the archive warehouse, V dpi Configuring the volume of the object for the ith archive storehouse, V td The specific calculation formula for the space volume of the channel area is as follows:,A td 、B td 、C td the width, length and height of the channel region respectively; the dynamic obstacle detection unit detects the number n of real-time dynamic obstacles in the archive warehouse da And remaining channel usable area A sy Calculating the real-time dynamic obstacle distribution density F D The specific formula is as follows: />The calculation formula of the available area of the residual channel is as follows:,A FP configuring the area of the articles on the access area for non-archival storage, A DP Allocating the area of the articles on the channel area for the archive warehouse, and calculating the real-time dynamic barrier distribution density F D And saturation dynamic barrier distribution density F Y Comparing, and judging that dynamic obstacle exists when the calculated value is larger than or equal to the preset value, wherein the dynamic obstacle coefficient X at the moment DT The calculation formula of (2) is as follows: />The method comprises the steps of carrying out a first treatment on the surface of the The alarm output unit sends an alarm to the archive warehouse management center when any one of the detection units detects an obstacle.
The channel obstacle processing module processes all existing channel obstacles after receiving the alarm, and automatically records the alarm receiving time and the channel obstacle clearing completion time.
The channel obstacle processing efficiency calculation module calculates a comprehensive channel obstacle coefficient by non-archive warehouse object configuration obstacle coefficients, archive warehouse object configuration obstacle coefficients and dynamic obstacle coefficients when sending an alarm, and calculates the channel obstacle processing efficiency based on the comprehensive channel obstacle coefficient and the channel obstacle processing time.
The channel obstacle processing efficiency calculation module comprises a data calling unit, a comprehensive channel obstacle coefficient calculation unit and a channel obstacle processing efficiency calculation unit, wherein the data calling unit is used for calling non-archive storehouse object configuration obstacle coefficients, dynamic obstacle coefficients, alarm receiving time during channel obstacle processing and channel obstacle clearing completion time when an alarm is sent; the comprehensive channel obstacle coefficient calculation unit is based on a non-archive storehouse object configuration obstacle coefficient X when sending an alarm FP Obstacle coefficient X for file warehouse configuration article DP Coefficient of dynamic disorder X DT Calculating the comprehensive channel obstruction coefficient X ZZ The specific formula of (2) is:e is a natural constant; the channel obstacle processing efficiency calculation unit is based on the comprehensive channel obstacle coefficient X ZZ Alarm receiving time T during lane obstacle handling js Channel obstacle clearing completion time T qw Calculating channel obstruction processing efficiency beta zc The specific formula of (2) is: />。
The database is used for recording the data of all modules in the system.
In this embodiment, it is specifically required to explain that all the preset values are selected based on actual needs, and the specific values are not limited herein.
As shown in fig. 2, the present embodiment provides an operation flow of a channel obstruction detection system for an archive warehouse, which includes the following steps:
s1: retrieving configuration article information in the archive warehouse, performing full network retrieval based on the function and the name of the configuration article, and recording the retrieved configuration article information;
s2: reconstructing the retrieved configuration article standard three-dimensional model based on the recorded retrieved article information, and marking the configuration article standard three-dimensional model by using the configuration article function, name and model;
s3: the method comprises the steps of setting channel obstacle judging standards, wherein the channel obstacle judging standards comprise static obstacle judging standards and dynamic obstacle judging standards;
s4: monitoring article information in the archive warehouse in real time by using cameras, and sending image data recorded by different cameras to an article information configuration identification module;
s5: after a series of processing is carried out on the received image data, whether the articles in the archive warehouse are configured articles or not is identified, the configured articles display the identified names and the types of the articles, and the non-configured articles display the articles as non-archive warehouse configured articles;
s6: detecting a channel obstacle based on the configuration article information identification result, and sending an alarm when the channel obstacle is judged to exist;
s7: processing all existing channel barriers after receiving the alarm, and automatically recording the alarm receiving time and the channel barrier cleaning completion time;
s8: calculating a comprehensive channel obstacle coefficient by using the non-archive storehouse object configuration obstacle coefficient, the archive storehouse object configuration obstacle coefficient and the dynamic obstacle coefficient when sending the alarm, and calculating the channel obstacle processing efficiency based on the comprehensive channel obstacle coefficient and the channel obstacle processing time.
Finally: the foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (6)
1. A channel obstacle detection system for a file warehouse is characterized in that: comprising the following steps:
a configuration article information input module: retrieving configuration article information in the archive warehouse, performing full network retrieval based on the function and the name of the configuration article, and recording the retrieved configuration article information;
configuring a standard three-dimensional model reconstruction module of the article: reconstructing the retrieved configuration article standard three-dimensional model based on the recorded retrieved article information, and marking the configuration article standard three-dimensional model by using the configuration article function, name and model;
the channel obstacle judgment standard setting module: the method comprises the steps of setting channel obstacle judging standards, wherein the channel obstacle judging standards comprise static obstacle judging standards and dynamic obstacle judging standards;
an article online monitoring module is configured: monitoring article information in the archive warehouse in real time by using cameras, and sending image data recorded by different cameras to an article information configuration identification module;
a configuration article information identification module: after a series of processing is carried out on the received image data, whether the articles in the archive warehouse are configured articles or not is identified, the configured articles display the identified names and the types of the articles, and the non-configured articles display the articles as non-archive warehouse configured articles;
the channel obstacle detection module: detecting a channel obstacle based on the configuration article information identification result, and sending an alarm when the channel obstacle is judged to exist;
the channel obstacle processing module: processing all existing channel barriers after receiving the alarm, and automatically recording the alarm receiving time and the channel barrier cleaning completion time;
the channel obstacle processing efficiency calculation module: calculating a comprehensive channel obstacle coefficient by using the non-archive storehouse object configuration obstacle coefficient, the archive storehouse object configuration obstacle coefficient and the dynamic obstacle coefficient when sending the alarm, and calculating the channel obstacle processing efficiency based on the comprehensive channel obstacle coefficient and the channel obstacle processing time.
2. A system for detecting a passage obstacle for a archive warehouse as claimed in claim 1, wherein: the configuration article information input module comprises a configuration article information calling unit, a networking searching unit, a searching information recording unit and a data output unit, wherein the configuration article information calling unit calls the name, the model and the function of the configuration article in the archive warehouse after being authorized; the networking retrieval unit is communicated with the Internet and then inputs the function and the name of the configuration object of the file warehouse to retrieve the information of the configuration object respectively; the searching information recording unit is used for recording the searched name and model of the configuration article, the size data of the contained accessories, the connecting mode of the used accessories and the full-angle overall appearance picture; and the data output unit sends the recorded retrieval information to a configuration article standard three-dimensional model reconstruction module.
3. A system for detecting a passage obstacle for a archive warehouse as claimed in claim 1, wherein: the standard three-dimensional model reconstruction module of the configuration article comprises a data receiving unit, an accessory model building unit, a three-dimensional model combination unit of the configuration article, a qualification identification unit of a finished product model, a model marking unit and an automatic backup unit, wherein the data receiving unit is used for receiving the recorded retrieved name, model number, size data of the accessory, connecting mode of the accessory and full-angle overall appearance picture of the configuration article; the accessory model building unit builds an accessory model in modeling software based on the size information of accessories contained in the article; the three-dimensional model combination unit of the configuration article assembles the accessory model according to the retrieved accessory connection mode; the finished product model qualification identifying unit acquires full-angle overall appearance pictures of the configured article finished product model obtained after combination, compares the full-angle overall appearance pictures with the retrieved article entity full-angle overall appearance pictures one by one, judges that the finished product model is qualified when the contrast difference of the two pictures is lower than the preset contrast difference of the pictures, reserves and identifies the qualified finished product model and marks the qualified finished product model as a configured article standard three-dimensional model, otherwise judges that the finished product model is unqualified, and needs to be reconstructed for the unqualified finished product model until the unqualified finished product model is qualified; the model labeling unit labels the standard three-dimensional model of the configuration object by using the function, the name and the model of the configuration object; the automatic backup unit is used for automatically backing up the standard three-dimensional model of the configuration object.
4. A system for detecting a passage obstacle for a archive warehouse as claimed in claim 1, wherein: the configuration article information identification module comprises a real-time image data receiving unit, a time frame ordering unit, an image segmentation unit, a plane contour information extraction unit, an article three-dimensional contour combination unit, an article three-dimensional contour cleaning unit, a three-dimensional contour information matching unit, an information identification unit and an identification result output unit, wherein the real-time image data receiving unit receives image data recorded by different cameras in real time; the time frame ordering unit orders the received image data according to the time frames, and uses different camera image data of the same time frame as the same group of image data and marks the same group of image data by the time frames; the image segmentation unit segments the acquired picture information by using a complex scene image semantic segmentation algorithm of the improved PSPNet to obtain multi-angle images of different articles; the plane contour information extraction unit is used for extracting plane contour information of the article; the article three-dimensional contour combining unit is used for combining and reconstructing the obtained article plane contour information with different angles to obtain an article three-dimensional contour; the article three-dimensional contour cleaning unit filters and denoises the reconstructed article three-dimensional contour to remove redundant contour points; the three-dimensional contour information matching unit matches the three-dimensional contour of the cleaned article with the contour of the standard three-dimensional model of the configured article, and counts the contour volume V of the three-dimensional contour of the article which can be overlapped with the contour of the standard three-dimensional model of the configured article ch And a contour volume V which cannot be coincident bc And calculates the profile matching degree alpha lk The specific formula is as follows:the method comprises the steps of carrying out a first treatment on the surface of the The information identification unit compares the calculated maximum profile matching degree with a preset profile matching degree, two articles which are larger than or equal to the preset profile matching degree and are judged to be matched are the same article, two articles which are smaller than the preset profile matching degree and are judged to be matched are not the same article, the name and the model of the matched article are displayed when the matching is successful, and the article is displayed as a non-archive storehouse configuration article when the matching is failedA product; the identification result output unit is used for outputting the identification result to the channel obstacle detection module.
5. A system for detecting a passage obstacle for a archive warehouse as claimed in claim 1, wherein: the channel obstacle detection module comprises an identification result receiving unit, a non-archive warehouse configuration article obstacle detection unit, an archive warehouse configuration article obstacle detection unit, a dynamic obstacle detection unit and an alarm output unit, wherein the identification result receiving unit is used for receiving real-time identification results of articles in the archive warehouse; the non-archival repository configuration object obstacle detection unit is used for detecting the actual residence time of the non-archival repository configuration object, and judging that the non-archival repository configuration object obstacle exists when the actual residence time is greater than or equal to the preset time, and the non-archival repository object configuration obstacle coefficient X FP The calculation formula of (2) is as follows:,n cl configuring the quantity of the articles for non-archive storehouse, T cli Configuring the actual residence time of the item for the ith non-archive warehouse, T yl For a preset maximum permissible dwell time, V cli Configuring the contour volume of the item for the ith non-archive storehouse, V kf The volume of the built-in space of the archive storehouse is; the archive storehouse configuration article obstacle detection unit is used for detecting the relation between the width, length and height of the archive storehouse configuration article on the channel and the actual passing width, length and height of the channel and respective preset values thereof, judging that the archive storehouse configuration article obstacle exists when the maximum allowable width, length and height of the archive storehouse configuration article on the channel area are larger than or equal to the preset values, and judging that the archive storehouse configuration article obstacle exists when the actual passing width, length and height of the channel area are smaller than or equal to the preset values DP The calculation formula of (2) is as follows:,n dp configuring articles for archival repositoryNumber of V dpi Configuring the volume of the object for the ith archive storehouse, V td The specific calculation formula for the space volume of the channel area is as follows: />,A td 、B td 、C td The width, length and height of the channel region respectively; the dynamic obstacle detection unit detects the number n of real-time dynamic obstacles in the archive warehouse da And remaining channel usable area A sy Calculating the real-time dynamic obstacle distribution density F D The specific formula is as follows: />The calculation formula of the available area of the residual channel is as follows: />,A FP Configuring the area of the articles on the access area for non-archival storage, A DP Allocating the area of the articles on the channel area for the archive warehouse, and calculating the real-time dynamic barrier distribution density F D And saturation dynamic barrier distribution density F Y Comparing, and judging that dynamic obstacle exists when the calculated value is larger than or equal to the preset value, wherein the dynamic obstacle coefficient X at the moment DT The calculation formula of (2) is as follows: />The method comprises the steps of carrying out a first treatment on the surface of the The alarm output unit sends an alarm to the archive warehouse management center when any one of the detection units detects an obstacle.
6. A system for detecting a passage obstacle for a archive warehouse as claimed in claim 1, wherein: the channel obstacle processing efficiency calculation module comprises a data calling unit, a comprehensive channel obstacle coefficient calculation unit and a channel obstacle processing efficiency calculation unit, wherein the data calling unit is used for calling non-archive storehouse object configuration obstacle coefficients, dynamic obstacle coefficients and channels when sending alarmsAlarm receiving time and channel obstacle clearing completion time during obstacle processing; the comprehensive channel obstacle coefficient calculation unit is based on a non-archive storehouse object configuration obstacle coefficient X when sending an alarm FP Obstacle coefficient X for file warehouse configuration article DP Coefficient of dynamic disorder X DT Calculating the comprehensive channel obstruction coefficient X ZZ The specific formula of (2) is:e is a natural constant; the channel obstacle processing efficiency calculation unit is based on the comprehensive channel obstacle coefficient X ZZ Alarm receiving time T during lane obstacle handling js Channel obstacle clearing completion time T qw Calculating channel obstruction processing efficiency beta zc The specific formula of (2) is: />。
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410147112.3A CN117690122B (en) | 2024-02-02 | 2024-02-02 | Channel obstacle detection system for archive warehouse |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410147112.3A CN117690122B (en) | 2024-02-02 | 2024-02-02 | Channel obstacle detection system for archive warehouse |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117690122A true CN117690122A (en) | 2024-03-12 |
CN117690122B CN117690122B (en) | 2024-04-26 |
Family
ID=90137530
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410147112.3A Active CN117690122B (en) | 2024-02-02 | 2024-02-02 | Channel obstacle detection system for archive warehouse |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117690122B (en) |
Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011109286A (en) * | 2009-11-16 | 2011-06-02 | Alpine Electronics Inc | Vehicle periphery-monitoring device and vehicle periphery-monitoring method |
CN105701453A (en) * | 2016-01-04 | 2016-06-22 | 中南大学 | Railway ballast vehicle with obstacle identification system and obstacle identification method |
CN113821042A (en) * | 2021-11-23 | 2021-12-21 | 南京冈尔信息技术有限公司 | Cargo conveying obstacle identification system and method based on machine vision |
CN114463362A (en) * | 2021-12-29 | 2022-05-10 | 宜昌测试技术研究所 | Three-dimensional collision avoidance sonar obstacle detection method and system based on deep learning |
CN114556449A (en) * | 2020-12-17 | 2022-05-27 | 深圳市大疆创新科技有限公司 | Obstacle detection and re-identification method and device, movable platform and storage medium |
CN114708435A (en) * | 2022-04-24 | 2022-07-05 | 湖南科技大学 | Obstacle size prediction and uncertainty analysis method based on semantic segmentation |
CN114905512A (en) * | 2022-05-16 | 2022-08-16 | 安徽元古纪智能科技有限公司 | Panoramic tracking and obstacle avoidance method and system for intelligent inspection robot |
CN114995450A (en) * | 2022-06-21 | 2022-09-02 | 上海托旺数据科技有限公司 | Intelligent navigation method and system for blind people by using multi-eye stereoscopic vision |
KR20230013891A (en) * | 2021-07-20 | 2023-01-27 | (주)컨트롤웍스 | Apparatus and method for recognizing obstacle of autonomous driving tractor |
CN116363585A (en) * | 2023-03-20 | 2023-06-30 | 上海倍肯智能科技有限公司 | On-line monitoring method and system for power transmission line |
CN116503803A (en) * | 2023-04-27 | 2023-07-28 | 上海木蚁机器人科技有限公司 | Obstacle detection method, obstacle detection device, electronic device and storage medium |
CN116597122A (en) * | 2023-05-17 | 2023-08-15 | 西安深信科创信息技术有限公司 | Data labeling method, device, electronic equipment and storage medium |
-
2024
- 2024-02-02 CN CN202410147112.3A patent/CN117690122B/en active Active
Patent Citations (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2011109286A (en) * | 2009-11-16 | 2011-06-02 | Alpine Electronics Inc | Vehicle periphery-monitoring device and vehicle periphery-monitoring method |
CN105701453A (en) * | 2016-01-04 | 2016-06-22 | 中南大学 | Railway ballast vehicle with obstacle identification system and obstacle identification method |
CN114556449A (en) * | 2020-12-17 | 2022-05-27 | 深圳市大疆创新科技有限公司 | Obstacle detection and re-identification method and device, movable platform and storage medium |
KR20230013891A (en) * | 2021-07-20 | 2023-01-27 | (주)컨트롤웍스 | Apparatus and method for recognizing obstacle of autonomous driving tractor |
CN113821042A (en) * | 2021-11-23 | 2021-12-21 | 南京冈尔信息技术有限公司 | Cargo conveying obstacle identification system and method based on machine vision |
CN114463362A (en) * | 2021-12-29 | 2022-05-10 | 宜昌测试技术研究所 | Three-dimensional collision avoidance sonar obstacle detection method and system based on deep learning |
CN114708435A (en) * | 2022-04-24 | 2022-07-05 | 湖南科技大学 | Obstacle size prediction and uncertainty analysis method based on semantic segmentation |
CN114905512A (en) * | 2022-05-16 | 2022-08-16 | 安徽元古纪智能科技有限公司 | Panoramic tracking and obstacle avoidance method and system for intelligent inspection robot |
CN114995450A (en) * | 2022-06-21 | 2022-09-02 | 上海托旺数据科技有限公司 | Intelligent navigation method and system for blind people by using multi-eye stereoscopic vision |
CN116363585A (en) * | 2023-03-20 | 2023-06-30 | 上海倍肯智能科技有限公司 | On-line monitoring method and system for power transmission line |
CN116503803A (en) * | 2023-04-27 | 2023-07-28 | 上海木蚁机器人科技有限公司 | Obstacle detection method, obstacle detection device, electronic device and storage medium |
CN116597122A (en) * | 2023-05-17 | 2023-08-15 | 西安深信科创信息技术有限公司 | Data labeling method, device, electronic equipment and storage medium |
Non-Patent Citations (2)
Title |
---|
杨鹏树;刘卉;王晓翠;王侨;孟志军;: "基于双目视觉的作物苗期障碍物三维信息检测方法", 农机化研究, no. 04, 7 July 2020 (2020-07-07) * |
艾青林;刘赛;沈智慧;: "基于双重配准的机器人双目视觉三维拼接方法研究", 机电工程, no. 10, 24 October 2018 (2018-10-24) * |
Also Published As
Publication number | Publication date |
---|---|
CN117690122B (en) | 2024-04-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112801050B (en) | Intelligent luggage tracking and monitoring method and system | |
US6993180B2 (en) | Method and system for automated grouping of images | |
EP0805405A2 (en) | Motion event detection for video indexing | |
CN111798456A (en) | Instance segmentation model training method and device and instance segmentation method | |
CN109409218A (en) | Reminding method, apparatus and system | |
CN109934104A (en) | The pedestrian retrieval method and system across camera lens identified again based on pedestrian | |
CN112383756B (en) | Video monitoring alarm processing method and device | |
CN110619308A (en) | Aisle sundry detection method, device, system and equipment | |
CN112307871A (en) | Information acquisition method and device, attention detection method, device and system | |
CN111784387A (en) | Multi-dimensional big data-based consumer brand loyalty analysis method | |
CN117690122B (en) | Channel obstacle detection system for archive warehouse | |
CN115497169A (en) | Warehouse operation behavior identification method, device and equipment | |
CN112214513A (en) | Intelligent manufacturing material management system | |
CN110110594B (en) | Product distribution identification method and device | |
CN115880626A (en) | Method and system for detecting shortage of goods and replenishing goods | |
CN108557364B (en) | Automatic inventory making method and device | |
CN110617670A (en) | Unmanned refrigerator based on image recognition and recognition method thereof | |
CN115131826A (en) | Article detection and identification method, and network model training method and device | |
CN114455255A (en) | Abnormal cigarette sorting error detection method based on multi-feature recognition | |
CN111179581B (en) | System and method for sharing bicycle ID matching based on vision | |
CN111382143A (en) | Data cleaning method and device and computer readable storage medium | |
CN111401370A (en) | Method, model and system for identifying junk images and assigning and managing tasks | |
CN111260716A (en) | Method, device, server and storage medium for determining commercial tenant seat interval | |
CN111310729B (en) | Method for acquiring purity of refrigerator based on image recognition technology and asset management system | |
CN112541550B (en) | Refrigerator integrity judgment method based on image classification and electronic equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |